A map generation device that detects a pre-specified target object based on image information obtained by imaging from each of a plurality of vehicles; estimates position information that is an absolute position of the detected target object, the position information being estimated based on a relative position of the detected target object and each vehicle imaging the image information in which the target object is detected, and position information that is an absolute position of each vehicle at a time of imaging the target object; and integrates matching target objects included in a plurality of estimated target objects, the matching target objects being integrated based on the position information of the respective target objects and the image information of the images in which the respective target objects are included, and a number and positions of the target objects being specified.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The map generation device according to claim 1, wherein the target objects are clustered by estimated positions of the target objects, and the number and positions of the target objects are specified based on differences between feature quantities of the target objects that are present in each cluster.
3. The map generation device according to claim 1, wherein the target objects are clustered based on estimated positions of the target objects and feature quantities of images of the target objects, and the number and positions of the target objects are specified based on feature quantity differences between the target objects that are present in each cluster.
6. The map generation device according to claim 1, the processor is further configured to, in a case in which the number and position of a target object have been specified from a number of the image information, the number being at least a pre-specified threshold, add or remove information of the target object on a pre-existing map and update the map.
8. The non-transitory recording medium according to claim 7, wherein the target objects are clustered by estimated positions of the target objects, and the number and positions of the target objects are specified based on differences between feature quantities of the target objects that are present in each cluster.
This invention relates to a non-transitory recording medium storing a program for detecting and tracking target objects in a monitored area. The problem addressed is accurately identifying and tracking multiple objects in dynamic environments where objects may overlap or move unpredictably, leading to errors in position estimation and object counting. The system captures image data of the monitored area and processes it to extract feature quantities representing characteristics of detected target objects. These objects are then clustered based on their estimated positions. Within each cluster, the system analyzes differences in feature quantities to determine the number of distinct objects and their precise positions. This approach improves accuracy by resolving ambiguities caused by overlapping or closely positioned objects. The method involves generating a feature quantity map from the image data, detecting target objects within the map, and estimating their positions. The clustering step groups objects based on spatial proximity, and the feature quantity differences within each cluster are used to refine the count and position estimates. This ensures reliable tracking even in crowded or cluttered scenes. The invention is particularly useful in surveillance, autonomous navigation, and robotics applications where precise object detection and tracking are critical. By leveraging feature quantity analysis within clusters, the system reduces false positives and improves tracking consistency compared to traditional methods that rely solely on position-based clustering.
9. The non-transitory recording medium according to claim 7, wherein the target objects are clustered based on estimated positions of the target objects and feature quantities of images of the target objects, and the number and positions of the target objects are specified based on feature quantity differences between the target objects that are present in each cluster.
12. The non-transitory recording medium according to claim 7, the map generation processing further comprising, in a case in which the number and position of a target object have been specified from a number of the image information, the number being at least a pre-specified threshold, adding or removing information of the target object on a pre-existing map and updating the map.
14. The map generation method according to claim 13, wherein the target objects are clustered by estimated positions of the target objects, and the number and positions of the target objects are specified based on differences between feature quantities of the target objects that are present in each cluster.
15. The map generation method according to claim 13, wherein the target objects are clustered based on estimated positions of the target objects and feature quantities of images of the target objects, and the number and positions of the target objects are specified based on feature quantity differences between the target objects that are present in each cluster.
18. The map generation method according to claim 13, further comprising, in a case in which the number and position of a target object have been specified from a number of the image information, the number being at least a pre-specified threshold, adding or removing information of the target object on a pre-existing map and updating the map.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 17, 2020
November 1, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.